{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-local-feature-descriptors-with","title":"Learning local feature descriptors with triplets and shallow convolutional neural networks","arxiv_id":null,"date":"2016-09-01","proceeding":"British Machine Vision Conference 2016 9","authors":["V. Balntas","E. Riba","D. Ponsa","and K. Mikolajczyk."],"abstract":"It has recently been demonstrated that local feature descriptors based on convolutional\r\nneural networks (CNN) can significantly improve the matching performance. Previous\r\nwork on learning such descriptors has focused on exploiting pairs of positive and\r\nnegative patches to learn discriminative CNN representations. In this work, we propose\r\nto utilize triplets of training samples, together with in-triplet mining of hard negatives.\r\nWe show that our method achieves state of the art results, without the computational\r\noverhead typically associated with mining of negatives and with lower complexity of the\r\nnetwork architecture. We compare our approach to recently introduced convolutional\r\nlocal feature descriptors, and demonstrate the advantages of the proposed methods in\r\nterms of performance and speed. We also examine different loss functions associated\r\nwith triplets.","url_abs":"http://www.bmva.org/bmvc/2016/papers/paper119/paper119.pdf","url_pdf":"http://www.bmva.org/bmvc/2016/papers/paper119/paper119.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-local-feature-descriptors-with","repo_url":"https://github.com/vbalnt/tfeat","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"learning-local-feature-descriptors-with","repo_url":"https://github.com/kornia/kornia/blob/master/kornia/feature/tfeat.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}